Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Laser point cloud semantic segmentation method and device

A laser point cloud and semantic segmentation technology, applied in the field of data processing, can solve the problem of low precision of laser point cloud semantic segmentation

Active Publication Date: 2020-07-31
BEIJING JINGWEI HIRAIN TECH CO INC
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the disordered and unstructured characteristics of laser point cloud data, and may have different densities in 3D space, deep learning applications face great challenges in the task of laser point cloud semantic segmentation. Laser point cloud semantic segmentation The accuracy is generally not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Laser point cloud semantic segmentation method and device
  • Laser point cloud semantic segmentation method and device
  • Laser point cloud semantic segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] At present, when using deep learning for laser point cloud semantic segmentation, some technicians have proposed a laser point cloud semantic segmentation method based on position attention and auxiliary network. The method is specifically: obtain the training set T and the test set V; Construct a 3D point cloud semantic segmentation network, and set the loss function of the network, which includes sequentially cascaded feature downsampling network, position attention module, feature upsampling network and auxiliary network; use the training set T to segment the network Perform P rounds of supervised training: adjust the network parameters according to the loss function during each round of training, and use the network model with the highest segmentation accuracy as the trained network model after the P round of training is completed; input the test set V to Semantic segmentation is performed in the trained network model to obtain the segmentation result of each point, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a laser point cloud semantic segmentation method and device. The method comprises the steps: performing two-dimensional projection on the obtained original laser point cloud data to obtain a two-dimensional image; performing convolutional feature extraction on the two-dimensional image based on a convolutional network, and obtaining a front view feature and a top view feature; fusing the front view feature, the top view feature and a three-dimensional feature of point cloud in original laser point cloud data to obtain a target laser point cloud feature, and inputting the target laser point cloud feature into a PointNet network for semantic segmentation. According to the method, the visual field range of each pixel point can be expanded through the N-channel featureof the front view after convolution feature extraction and the M-channel feature of the top view after convolution feature extraction, and the feature information of the single laser point cloud can be expanded by fusing the front view feature, the top view feature and the three-dimensional feature of each laser point cloud in the original laser point cloud data.

Description

technical field [0001] The present invention relates to the technical field of data processing, and more specifically, to a laser point cloud semantic segmentation method and device. Background technique [0002] In recent years, with the widespread application of 3D sensors such as lidar in the fields of robotics and driverless driving, the application of deep learning semantic segmentation in laser point cloud data processing has become one of the research hotspots. The so-called laser point cloud data means that the scanned object is recorded in the form of points, each point contains three-dimensional coordinates, and some may contain color information (RGB) or reflection intensity information (Intensity). [0003] Due to the disordered and unstructured characteristics of laser point cloud data, and may have different densities in 3D space, deep learning applications face great challenges in the task of laser point cloud semantic segmentation. Laser point cloud semantic ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/34G06K9/62G06T7/11G06T7/62
CPCG06T7/11G06T7/62G06T2207/10028G06V10/267G06F18/253G06F18/214Y02A90/10
Inventor 李世明韩恒贵
Owner BEIJING JINGWEI HIRAIN TECH CO INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com